© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 30262
    Prev
    Next
    INDEX
    Explanations

    the words "we," "us," "our," and "ourselves" in the context of doing or needing to do something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»ĻæĪij
    -0.13
    让æĪij
    -0.12
     saya
    -0.10
     himself
    -0.09
     my
    -0.09
     мне
    -0.09
     me
    -0.09
     mij
    -0.08
     bana
    -0.08
     μοÏħ
    -0.08
    POSITIVE LOGITS
     ourselves
    0.42
     our
    0.23
    ours
    0.19
    æĪij们çļĦ
    0.19
    ï¼ĮæĪij们
    0.19
    Ñħодим
    0.19
     we
    0.18
    æĪij们
    0.17
    —we
    0.17
     ours
    0.17
    Activations Density 0.755%

    No Known Activations